Search Results for author:
Found 11 papers, 8 papers with code
Evaluating Machine Accuracy on ImageNet
We perform an in-depth evaluation of human accuracy on the ImageNet dataset.
Language models scale reliably with over-training and on downstream tasks
We fit scaling laws that extrapolate in both the number of model parameters and the ratio of training tokens to parameters.
Data Filtering Networks
Our key finding is that the quality of a network for filtering is distinct from its performance on downstream tasks: for instance, a model that performs well on ImageNet can yield worse training sets than a model with low ImageNet accuracy that is trained on a small amount of high-quality data.
Neural Priming for Sample-Efficient Adaptation
Performing lightweight updates on the recalled data significantly improves accuracy across a variety of distribution shift and transfer learning benchmarks.
DataComp: In search of the next generation of multimodal datasets
Multimodal datasets are a critical component in recent breakthroughs such as Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model architectures or training algorithms.
Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text
We release Multimodal C4, an augmentation of the popular text-only C4 corpus with images interleaved.
Neural Radiance Field Codebooks
Compositional representations of the world are a promising step towards enabling high-level scene understanding and efficient transfer to downstream tasks.
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)
Contrastively trained language-image models such as CLIP, ALIGN, and BASIC have demonstrated unprecedented robustness to multiple challenging natural distribution shifts.
Ranked #94 on
Image Classification
on ObjectNet
(using extra training data)
The ISO Standard for Dialogue Act Annotation, Second Edition
ISO standard 24617-2 for dialogue act annotation, established in 2012, has in the past few years been used both in corpus annotation and in the design of components for spoken and multimodal dialogue systems.
Neural Kernels Without Tangents
We investigate the connections between neural networks and simple building blocks in kernel space.
The DialogBank
Some of these dialogues have been taken from existing corpora and have been re-annotated according to the ISO standard; others have been annotated directly according to the standard.
